The Agent Skills Directory

[SAFE]: The skill consists of instructional templates and does not perform code execution, network requests, or sensitive file access.
[SAFE]: No obfuscation or hidden content was found in the skill's library or reference documents.
[SAFE]: Roster validation and human-in-the-loop checkpoints are built into the planning process as security safeguards.
[PROMPT_INJECTION]: The skill incorporates user-supplied tasks into agent prompts, creating a surface for indirect prompt injection. This is a functional requirement of a planner and is addressed by the skill's structured format and output validation.

debate-agenda